ASSET Seminar: “Statistical Methods for Trustworthy Language Modeling” (Tatsu Hashimoto, Stanford University)
Raisler Lounge (Room 225), Towne Building 220 South 33rd Street, PhiladelphiaABSTRACT: Language models work well, but they are far from trustworthy. Major open questions remain on high-stakes issues such as detecting benchmark contamination, identifying LM-generated text, and reliably generating factually […]